Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag this as a non-read-only, destructive tool, so the burden is lighter. The description nonetheless adds high-value behavioral context the annotations cannot: accepting a recommendation mutates the template immediately and must be gated behind user agreement via confirmed:true, which is the key safety nuance for this tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded purpose sentence followed by a compact, scannable action/parameter breakdown with no filler. The parenthetical enumerations lean on schema data, but they earn their place by binding parameters to their action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-mode tool with no output schema, the description covers every action, its inputs, and the one dangerous path (accept + confirmed). What each action returns and validation constraints (lengths, maxItems) are left to the schema, which is acceptable, but return behavior for a destructive mutation is a remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 12 parameters at 67% schema coverage, the description's action-to-parameter mapping (which fields belong to save_injury vs set_status vs review_recommendation) is genuinely additive because JSON Schema cannot express conditional per-action requirements. It does not mention idempotency_key, so the coverage is good but not complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a verb+resource (change injury memories, answer recommendations) and the three named actions (save_injury, set_status, review_recommendation) make the scope concrete. It implicitly contrasts with the read_memory sibling by being the mutation counterpart, but never names that sibling, so the differentiation is inferable rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Each action is paired with the parameters it expects, and review_recommendation carries a real precondition (accept changes the template at once and needs confirmed:true after the user agrees). There is no explicit when-not-to-use guidance or routing to read_memory/delete for the non-mutating cases, so it falls short of the 5 bar.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.